[Bug] I encountered this problem when deploying flask service. I set the parameters CUDA_VISIBLE_DEVICES=3 when I started the service

[nixsui]

Checklist

• [X] 1. I have searched related issues but cannot get the expected help.
• [X] 2. The bug has not been fixed in the latest version.
• [X] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

an illegal memory access was encountered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

code: page_recognize_service = PageRecognizeService( model_path=app.config['PPT_PAGE_RECOGNIZE_MODEL_PATH'], device_type=app.config['DEVICE_TYPE'], )

page_content_extract_service = PageContentExtractService( model_path=app.config['PPT_PAGE_CONTENT_EXTRACT_MODEL_PATH'], device_type=app.config['DEVICE_TYPE'], )

class XXXAPI: def init(self): pass

Environment

pytorch2.0.1-cu11.7

Error traceback

No response